1 | #region License Information
|
---|
2 | /* HeuristicLab
|
---|
3 | * Copyright (C) 2002-2011 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
4 | *
|
---|
5 | * This file is part of HeuristicLab.
|
---|
6 | *
|
---|
7 | * HeuristicLab is free software: you can redistribute it and/or modify
|
---|
8 | * it under the terms of the GNU General Public License as published by
|
---|
9 | * the Free Software Foundation, either version 3 of the License, or
|
---|
10 | * (at your option) any later version.
|
---|
11 | *
|
---|
12 | * HeuristicLab is distributed in the hope that it will be useful,
|
---|
13 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
14 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
15 | * GNU General Public License for more details.
|
---|
16 | *
|
---|
17 | * You should have received a copy of the GNU General Public License
|
---|
18 | * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
|
---|
19 | */
|
---|
20 | #endregion
|
---|
21 |
|
---|
22 | using System;
|
---|
23 | using System.Collections.Generic;
|
---|
24 | using System.Drawing;
|
---|
25 | using System.Linq;
|
---|
26 | using HeuristicLab.Common;
|
---|
27 | using HeuristicLab.Core;
|
---|
28 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
29 | using HeuristicLab.Problems.DataAnalysis;
|
---|
30 |
|
---|
31 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
32 | /// <summary>
|
---|
33 | /// Represents a support vector solution for a regression problem which can be visualized in the GUI.
|
---|
34 | /// </summary>
|
---|
35 | [Item("SupportVectorRegressionSolution", "Represents a support vector solution for a regression problem which can be visualized in the GUI.")]
|
---|
36 | [StorableClass]
|
---|
37 | public sealed class SupportVectorRegressionSolution : RegressionSolution {
|
---|
38 |
|
---|
39 | public new SupportVectorRegressionModel Model {
|
---|
40 | get { return (SupportVectorRegressionModel)base.Model; }
|
---|
41 | }
|
---|
42 |
|
---|
43 | //IRegressionModel IRegressionSolution.Model {
|
---|
44 | // get { return model; }
|
---|
45 | //}
|
---|
46 | //IDataAnalysisModel IDataAnalysisSolution.Model {
|
---|
47 | // get { return model; }
|
---|
48 | //}
|
---|
49 |
|
---|
50 | //[Storable]
|
---|
51 | //private IRegressionProblemData problemData;
|
---|
52 | //public IRegressionProblemData ProblemData {
|
---|
53 | // get { return problemData; }
|
---|
54 | //}
|
---|
55 | //IDataAnalysisProblemData IDataAnalysisSolution.ProblemData {
|
---|
56 | // get { return ProblemData; }
|
---|
57 | //}
|
---|
58 |
|
---|
59 | [Storable]
|
---|
60 | private double lowerEstimationLimit;
|
---|
61 | public double LowerEstimationLimit {
|
---|
62 | get { return lowerEstimationLimit; }
|
---|
63 | }
|
---|
64 |
|
---|
65 | [Storable]
|
---|
66 | private double upperEstimationLimit;
|
---|
67 | public double UpperEstimationLimit {
|
---|
68 | get { return upperEstimationLimit; }
|
---|
69 | }
|
---|
70 |
|
---|
71 | private List<string> inputVariables;
|
---|
72 | [Storable]
|
---|
73 | private IEnumerable<string> InputVariablesStorable {
|
---|
74 | get { return inputVariables; }
|
---|
75 | set { inputVariables = new List<string>(value); }
|
---|
76 | }
|
---|
77 |
|
---|
78 |
|
---|
79 | //public event EventHandler ModelChanged;
|
---|
80 |
|
---|
81 | //public event EventHandler ProblemDataChanged;
|
---|
82 |
|
---|
83 | public Dataset SupportVectors {
|
---|
84 | get { return CalculateSupportVectors(); }
|
---|
85 | }
|
---|
86 |
|
---|
87 | //private List<double> estimatedValues;
|
---|
88 |
|
---|
89 | [StorableConstructor]
|
---|
90 | private SupportVectorRegressionSolution(bool deserializing) : base(deserializing) { }
|
---|
91 | private SupportVectorRegressionSolution(SupportVectorRegressionSolution original, Cloner cloner)
|
---|
92 | : base(original, cloner) {
|
---|
93 | //problemData = cloner.Clone(original.problemData);
|
---|
94 | //model = cloner.Clone(original.model);
|
---|
95 | inputVariables = new List<string>(original.inputVariables);
|
---|
96 | lowerEstimationLimit = original.lowerEstimationLimit;
|
---|
97 | upperEstimationLimit = original.upperEstimationLimit;
|
---|
98 | }
|
---|
99 | public SupportVectorRegressionSolution(SupportVectorRegressionModel model, IRegressionProblemData problemData, IEnumerable<string> inputVariables, double lowerEstimationLimit, double upperEstimationLimit)
|
---|
100 | : base(model, problemData) {
|
---|
101 | //this.problemData = problemData;
|
---|
102 | //this.model = model;
|
---|
103 | this.inputVariables = new List<string>(inputVariables);
|
---|
104 | this.lowerEstimationLimit = lowerEstimationLimit;
|
---|
105 | this.upperEstimationLimit = upperEstimationLimit;
|
---|
106 | }
|
---|
107 |
|
---|
108 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
109 | return new SupportVectorRegressionSolution(this, cloner);
|
---|
110 | }
|
---|
111 |
|
---|
112 | protected override void OnProblemDataChanged(EventArgs e) {
|
---|
113 | Model.Model.SupportVectorIndizes = new int[0];
|
---|
114 | base.OnProblemDataChanged(e);
|
---|
115 | }
|
---|
116 |
|
---|
117 | //public IEnumerable<double> GetEstimatedValues(IEnumerable<int> rows) {
|
---|
118 | // if (estimatedValues == null) RecalculateEstimatedValues();
|
---|
119 | // foreach (int row in rows)
|
---|
120 | // yield return estimatedValues[row];
|
---|
121 | //}
|
---|
122 |
|
---|
123 | //public override IEnumerable<double> EstimatedValues {
|
---|
124 | // get {
|
---|
125 | // if (estimatedValues == null) RecalculateEstimatedValues();
|
---|
126 | // return estimatedValues;
|
---|
127 | // }
|
---|
128 | //}
|
---|
129 |
|
---|
130 | //public override IEnumerable<double> EstimatedTrainingValues {
|
---|
131 | // get {
|
---|
132 | // return GetEstimatedValues(ProblemData.TrainingIndizes);
|
---|
133 | // }
|
---|
134 | //}
|
---|
135 |
|
---|
136 | //public override IEnumerable<double> EstimatedTestValues {
|
---|
137 | // get {
|
---|
138 | // return GetEstimatedValues(ProblemData.TestIndizes);
|
---|
139 | // }
|
---|
140 | //}
|
---|
141 |
|
---|
142 | private Dataset CalculateSupportVectors() {
|
---|
143 | if (Model.Model.SupportVectorIndizes.Length == 0)
|
---|
144 | return new Dataset(new List<string>(), new double[0, 0]);
|
---|
145 |
|
---|
146 | double[,] data = new double[Model.Model.SupportVectorIndizes.Length, ProblemData.Dataset.Columns];
|
---|
147 | for (int i = 0; i < Model.Model.SupportVectorIndizes.Length; i++) {
|
---|
148 | for (int column = 0; column < ProblemData.Dataset.Columns; column++)
|
---|
149 | data[i, column] = ProblemData.Dataset[Model.Model.SupportVectorIndizes[i], column];
|
---|
150 | }
|
---|
151 | return new Dataset(ProblemData.Dataset.VariableNames, data);
|
---|
152 | }
|
---|
153 |
|
---|
154 | //protected override void RecalculateEstimatedValues() {
|
---|
155 | // Dataset dataset = problemData.Dataset;
|
---|
156 | // string targetVariable = problemData.TargetVariable;
|
---|
157 | // IEnumerable<string> allowedInputVariables = problemData.InputVariables.CheckedItems.Select(x => x.Value);
|
---|
158 | // int start = 0;
|
---|
159 | // int end = dataset.Rows;
|
---|
160 | // IEnumerable<int> rows = Enumerable.Range(start, end - start);
|
---|
161 | // SVM.Problem problem = SupportVectorMachineUtil.CreateSvmProblem(dataset, targetVariable, allowedInputVariables, rows);
|
---|
162 | // SVM.Problem scaledProblem = SVM.Scaling.Scale(Model.RangeTransform, problem);
|
---|
163 |
|
---|
164 | // estimatedValues = (from row in Enumerable.Range(0, scaledProblem.Count)
|
---|
165 | // let prediction = SVM.Prediction.Predict(Model.Model, scaledProblem.X[row])
|
---|
166 | // let boundedX = Math.Min(UpperEstimationLimit, Math.Max(LowerEstimationLimit, prediction))
|
---|
167 | // select double.IsNaN(boundedX) ? UpperEstimationLimit : boundedX).ToList();
|
---|
168 | //}
|
---|
169 | }
|
---|
170 | }
|
---|